Render me real?

Abstract

Figure 1: Male avatar rendered in different visual styles, ranging from realistic to abstract, based on the results in Section 5. AbstractThe realistic depiction of lifelike virtual humans has been the goal of many movie makers in the last decade. Recently, films such as Tron: Legacy and The Curious Case of Benjamin Button have produced highly realistic characters. In the real-time domain, there is also a need to deliver realistic virtual characters, with the increase in popularity of interactive drama video games (such as L.A. Noire TM or Heavy Rain TM ). There have been mixed reactions from audiences to lifelike characters used in movies and games, with some saying that the increased realism highlights subtle imperfections, which can be disturbing. Some developers opt for a stylized rendering (such as cartoon-shading) to avoid a negative reaction [Thompson 2004]. In this paper, we investigate some of the consequences of choosing realistic or stylized rendering in order to provide guidelines for developers for creating appealing virtual characters. We conducted a series of psychophysical experiments to determine whether render style affects how virtual humans are perceived. Motion capture with synchronized eye-tracked data was used throughout to animate custom-made virtual model replicas of the captured actors.

A Comparison of Avatar-, Video-, and Robot-Mediated Interaction on Users’ Trust in Expertise

“…They observed high correlation between professional appearances in avatar design with high credibility measures. McDonnell et al (2012) showed that small differences in rendering styles can influence perceptual judgments of computer graphic characters. Hyde et al (2015) found that adjusting the expressiveness of interactive animated avatars may be a simple way to influence people's social judgments and willingness to collaborate with animated avatars.…”

A comparison of speaking up behavior during conflict with real and virtual humans

“…This definition encapsulates the two main continuums of interest when considering a virtual human: its visual realism (McDonnell, Breidt, & Bülthoff, 2012) and its behavioral realism (von der Pütten et al). Visual realism can be influenced by a number of factors, including rendering style (McDonnell et al, 2012), animation quality (Maddock, Edge, & Sanchez, 2005), display characteristics (e.g. resolution, size) (Ni, Bowman, & Chen, 2006), and display modality (e.g.…”

“…Nowak et al found that agents with low anthropomorphism (a highly stylized cartoon face) evoked stronger feelings of social presence than high anthropomorphism agents (Nowak & Biocca, 2003). McDonnell et al found that participants rated cartoon faces with lower realism as more appealing and more friendly than slightly more realistic faces (McDonnell et al, 2012); however, highly realistic faces were rated as similarly appealing and friendly. Ring et al found an interaction effect between task domain (medicine vs. social dialog) and visual realism on how an agent was perceived (Ring et al); less realistic virtual humans were perceived as more likable in the social domain, but not in the medical.…”

Investigating Macroexpressions and Microexpressions in Computer Graphics Animated Faces

“…Although there have been great advances in modeling, rigging, rendering, motion capture and retargeting techniques -with the goal of escaping the "Uncanny Valley" (Alexander, Rogers, Lambeth, Chiang, & Debevec, 2009;McDonnell, Breidt, & Bülthoff, 2012) -the creation of realistic and convincing face behaviors for games and movies is still strongly dependent on animator skills. There are some studies about how to convey and evaluate a character's complex facial behaviors (Paleari & Lisetti, 2006;Bevacqua, Mancini, Niewiadomski, & Pelachaud, 2007;Rehm, 2008;Orvalho & Sousa, 2009;Niewiadomski, Hyniewska, & Pelachaud, 2009;Queiroz, Braun, et al, 2010;Demeure, Niewiadomski, & Pelachaud, 2011;de Melo, Carnevale, & Gratch, 2011;Xolocotzin Eligio, Ainsworth, & Crook, 2012), but few really focus on microexpressions (Zielke, Dufour, & Hardee, 2011).…”